Abstract
The machine learning-based virtual screening of molecular databases is a commonly used approach to identify hits. However, many aspects associated with training predictive models can influence the final performance and, consequently, the number of hits found. Thus, we performed a systematic study of the simultaneous influence of the proportion of negatives to positives in the testing set, the size of screening databases and the type of molecular representations on the effectiveness of classification. The results obtained for eight protein targets, five machine learning algorithms (SMO, Naïve Bayes, Ibk, J48 and Random Forest), two types of molecular fingerprints (MACCS and CDK FP) and eight screening databases with different numbers of molecules confirmed our previous findings that increases in the ratio of negative to positive training instances greatly influenced most of the investigated parameters of the ML methods in simulated virtual screening experiments. However, the performance of screening was shown to also be highly dependent on the molecular library dimension. Generally, with the increasing size of the screened database, the optimal training ratio also increased, and this ratio can be rationalized using the proposed cost-effectiveness threshold approach. To increase the performance of machine learning-based virtual screening, the training set should be constructed in a way that considers the size of the screening database.
Highlights
Machine learning (ML) methods are widely used in drug discovery to classify molecules as potentially active or inactive against a particular protein target
Five machine learning algorithms (Sequential Minimal Optimization–SMO, Naïve Bayes–Naïve Bayes classifier (NB), Ibk, J48 and Random Forest–RF) were used in the screening of eight screening libraries whose magnitudes were established to reflect the commercial collections of available compounds and combinatorial libraries that are often used in virtual screening [13]
We investigated the performance of a collection of machine learning algorithms in ligand-based virtual screening in cases in which the inactive to active training ratio and screening library size were iteratively changed
Summary
Machine learning (ML) methods are widely used in drug discovery to classify molecules as potentially active or inactive against a particular protein target. The vast majority of those methods require the preparation of a training set of compounds (supervised learning) that are used to develop a decision function that can be used for virtual screening (VS) of chemical libraries among particular activity classes [1]. The size of the screening library can vary from several hundred, especially in the case of in-house, reaction-based combinatorial libraries, to millions of compounds, which are available from commercial suppliers. The authors noted that the highest percentage of exclusive compounds was found for the first (90%) and the second group (~50%). Based on these outcomes and taking into account practical aspects of virtual screening, we focused our study on databases from the first two classes
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
